© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72353
    Prev
    Next
    INDEX
    Explanations

    occurrence of conditions and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hâte
    -1.38
     frequentemente
    -1.37
    好像
    -1.36
     varandra
    -1.34
    ɫ
    -1.33
     provenant
    -1.32
     participer
    -1.31
     rassemb
    -1.29
     aparentemente
    -1.28
     två
    -1.27
    POSITIVE LOGITS
     even
    2.33
     in
    1.61
     using
    1.57
     during
    1.55
     as
    1.49
     any
    1.47
     at
    1.44
     such
    1.43
     if
    1.41
     while
    1.41
    Activations Density 0.119%

    No Known Activations